Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / b4ef16334900af33bf4321f28c90f62bf32238cd / src / backends / neon
  1. b4ef163 IVGCVSW-7854 Remove/rewrite asserts in the backends. by Colm Donelan · 5 months ago
  2. 5e90b83 IVGCVSW-7569 GpuFsa Op: Add Reshape Operator by Declan-ARM · 5 months ago
  3. a4b6090 Add and tidy up activation and elementwise binary end to end tests by Teresa Charlin · 5 months ago
  4. a52bca2 IVGCVSW-7623: GpuFsa Op: Add Pool2d operator by Teresa Charlin · 5 months ago
  5. 829e13e IVGCVSW-7568 Implement Sub ElementwiseBinary operator GpuFsa by John Mcloughlin · 5 months ago
  6. e7d2785 IVGCVSW-7550 GpuFsa Op: Add ElementWiseBinary Operator ADD by Tracy Narine · 5 months ago
  7. 0d7963c Bugfix: Remove implicit sign conversion causing -Werror=sign-conversion by Francis Murtagh · 5 months ago
  8. 28658bc Fix for Resize with align corners = true creates a memory leak when using valgrind by Teresa Charlin · 6 months ago
  9. a7bd3fa IVGCVSW-7830 Remove Reshape where possible by Mike Kelly · 6 months ago
  10. a9c3267 IVGCVSW-8159 Fixed issues building with NDK r26 by Mike Kelly · 7 months ago
  11. 21a9f33 IVGCVSW-7835 Add ReverseV2 CL and Neon Workloads by Tianle Cheng · 8 months ago
  12. bba0d13 Removing explicit block on non constant bias in NEON CONV2D. by Colm Donelan · 8 months ago
  13. 363b572 Revert "Revert "MLCE-1093 Reshape and concat invalid results"" by Mike Kelly · 9 months ago
  14. 5008cb8 Revert "IVGCVSW-7850 block non const bias on NEON Depthwise conv." by Colm Donelan · 9 months ago
  15. 077cddb IVGCVSW-8055 Add support for GELU activation function. by Teresa Charlin · 10 months ago
  16. 6440ce8 IVGCVSW-7504 Create a backend specific optimization to fuse ADD+MUL+Add+(Activation) in CpuAcc by Tracy Narine · 9 months ago
  17. 0aa080d BugFix: ElementwiseBinary missing from NeonBackend activation fusion optimization by Teresa Charlin · 9 months ago
  18. 2be039b IVGCVSW-6964 Remove profiling detail for ConstTensorAsInputs Layers by John Mcloughlin · 11 months ago
  19. 9145e38 IVGCVSW-7505 Create FusedLayer and NeonFusedWorkload for AddMulAdd Neon kernel by Teresa Charlin · 11 months ago
  20. 5f94124 IVGCVSW-7964 Fix UnidirectionalSequenceLstm by Narumol Prangnawarat · 11 months ago
  21. 008270f Revert "MLCE-1093 Reshape and concat invalid results" by Nikhil Raj Arm · 11 months ago
  22. 4980e21 MLCE-1093 Reshape and concat invalid results by Mike Kelly · 11 months ago
  23. 8259941 Revert "IVGCVSW-6964 Remove profiling detail for ConstTensorAsInputs Layers" by john.mcloughlin · 11 months ago
  24. d1f0001 IVGCVSW-6964 Remove profiling detail for ConstTensorAsInputs Layers by John Mcloughlin · 11 months ago
  25. 7894ef9 IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (WorkloadFactory) by Cian McGriskin · 11 months ago
  26. 6627703 IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (ILayerSupport) by Francis Murtagh · 11 months ago
  27. 0f3e9a0 IVGCVSW-7635 Remove deprecated code due to be removed in 23.08 (SubgraphView) by Francis Murtagh · 11 months ago
  28. b4c4934 IVGCVSW-7880 Add check for FP16 backend support by Ryan OShea · 11 months ago
  29. 980446b Enable Slice EndToEndTests in all backends and Signed32 in CpuRef by Ryan OShea · 1 year, 1 month ago
  30. 7cbe781 MLCE-1092 Add Names to Workloads by Mike Kelly · 11 months ago
  31. 038f52b Update ACL pin to 16b37527906c68885f81a8db35f9d6040d73efec by Nikhil Raj · 11 months ago
  32. 4f9a6d6 Add datalayout to tensors in NeonStridedSliceWorkload by Teresa Charlin · 12 months ago
  33. 36e6eae IVGCVSW-2292 Tile Operator Neon Implementation by David Monahan · 11 months ago
  34. a638f10 IVGCVSW-7907 Model cannot use Subtensors by Mike Kelly · 11 months ago
  35. b6de7a1 IVGCVSW-7830 Clean up by Mike Kelly · 12 months ago
  36. 47016c0 IVGCVSW-7850 block non const bias on NEON Depthwise conv. by Colm Donelan · 11 months ago
  37. 53d858b IVGCVSW-7849 and IVGCVSW-7825 block non const bias on NEON CONV2D. by Colm Donelan · 12 months ago
  38. be06f10 IVGCVSW-7891 Failure in Nightly tests by Mike Kelly · 12 months ago
  39. 4cc341c IVGCVSW-7830 Add backend optimizations to remove Reshapes where possible by Mike Kelly · 12 months ago
  40. 2ea403d IVGCVSW-7785 3D tensors in BATCH_TO_SPACE and SPACE_TO_BATCH in CpuAcc & GpuAcc by Teresa Charlin · 1 year ago
  41. d29d09d Update ACL pin to c952596e70f2fe0073029f053e329a4e930ced8c by Nikhil Raj · 1 year ago
  42. a9c5c16 Update ACL pin to 043613fbb199e2c4fdd12c2c9a1785db9b0c45fa by Nikhil Raj · 1 year ago
  43. 8eece0a IVGCVSW-7791 Enable dynamic bias in Conv in CpuAcc and GpuAcc by Kevin May · 1 year, 1 month ago
  44. 5b70184 IVGCVSW-7789 Enable dynamic bias in Depthwise Convolution in CpuAcc by Teresa Charlin · 1 year, 1 month ago
  45. 71311e4 Fix incorrect validation of Unidirectional Sequence LSTM on Cl and Neon by Narumol Prangnawarat · 1 year, 1 month ago
  46. 270641b MLCE-1022 Fix failure on UnidirectionalSequenceLstm Operator by Narumol Prangnawarat · 1 year, 1 month ago
  47. f663d48 IVGCVSW-7732 Enable dynamic bias in FullyConnected in CpuAcc and GpuAcc by Teresa Charlin · 1 year, 2 months ago
  48. 34c1c38 IVGCVSW-7400 POW IVGCVSW-7278 SQUARED_DIFFERENCE to CpuAcc and GpuAcc by John Mcloughlin · 1 year, 1 month ago
  49. acedd85 Revert "IVGCVSW-7454 Enable dynamic bias in CpuAcc and GpuAcc in Conv2d DWConv and FC" by TeresaARM · 1 year, 2 months ago
  50. fecd9ed IVGCVSW-7454 Enable dynamic bias in CpuAcc and GpuAcc in Conv2d DWConv and FC by Teresa Charlin · 1 year, 2 months ago
  51. 6fba294 IVGCVSW-7454 Fix CpuAcc FC dynamic weights by Teresa Charlin · 1 year, 2 months ago
  52. 1fe6c81 IVGCVSW-7307 Add CpuAcc Batch MatMul Workload by Teresa Charlin · 1 year, 8 months ago
  53. 34336f9 Make Convert workloads use arm_compute::NECast in CpuAcc backend by Matthew Bentham · 1 year, 2 months ago
  54. cfbb271 Add unit test for Neon Convert workloads by Matthew Bentham · 1 year, 2 months ago
  55. acb3ec5 GitHub #719 Set quantization parameter scale to 1.0, instead of 0.0. by Teresa Charlin · 1 year, 3 months ago
  56. c5ee0d7 IVGCVSW-7197 Implement Pimpl Idiom for OptimizerOptions by John Mcloughlin · 1 year, 3 months ago
  57. ca5c82a IVGCVSW-7507 Pass m_Crops in BatchToSpaceND CpuAcc and GpuAcc workloads by Teresa Charlin · 1 year, 3 months ago
  58. c1c5f2a Remove GetGraph and include of Graph.hpp header from public header by Matthew Bentham · 1 year, 3 months ago
  59. 1a05aad Revert "IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layers" by Mike Kelly · 1 year, 3 months ago
  60. b75fc93 IVGCVSW-7454 Enable NonConstWeights in CpuAcc by Teresa Charlin · 1 year, 5 months ago
  61. 52e90bf IVGCVSW-3808 Deprecation notices for old ElementwiseBinary layers by Mike Kelly · 1 year, 4 months ago
  62. 3ec3077 IVGCVSW-3808 Add ElementwiseBinaryLayer by Mike Kelly · 1 year, 4 months ago
  63. d7fca09 IVGCVSW-7173 Add Rsqrt to Tosa Ref Backend by David Monahan · 1 year, 6 months ago
  64. c17a35f IVGCVSW-5128 Add EndToEnd test for REDUCE_SUM by Teresa Charlin · 1 year, 6 months ago
  65. 80f71a8 IVGCVSW-7211 Fix float16 operators being wrongly unsupported with android-nn-driver. by Cathal Corbett · 1 year, 6 months ago
  66. ec67a0f IVGCVSW-7209 Remove deprecated code due to be removed in 23.02 by Mike Kelly · 1 year, 7 months ago
  67. 6bc8525 IVGCVSW-6853 Rewrite BuildArmComputePermutationVector() by Teresa Charlin · 1 year, 7 months ago
  68. 3144159 IVGCVSW-7214 Disable BF16-Turbo-Mode and remove conversion layers by Ryan OShea · 1 year, 8 months ago
  69. 3c2795a IVGCVSW-7318 Support basic addition model in the TOSA Reference Backend by Ryan OShea · 1 year, 8 months ago
  70. a38da59 IVGCVSW-6496 Add EndToEnd Layer test for Batch MatMul Workload by Teresa Charlin · 1 year, 8 months ago
  71. 0f86ecf IVGCVSW-6494 Add CpuAcc Batch MatMul Workload Fp32 by Teresa Charlin · 1 year, 9 months ago
  72. 251fd95 IVGCVSW-7222 Fix incorrect kernel measurements in profiling output by Kevin May · 1 year, 9 months ago
  73. 5a3d200 IVGCVSW-7111 change backend deprecation from 22.11 to 23.08 by Jim Flynn · 1 year, 11 months ago
  74. d301c0a IVGCVSW-6889 Seg fault running ExeNet with --bf16-turbo-mode on fpga by Francis Murtagh · 1 year, 11 months ago
  75. d7ceec5 IVGCVSW-6896 Fix pre-import when using sync execute. by Colm Donelan · 2 years ago
  76. 626bd90 Revert "Revert "IVGCVSW-6873 Import inputs but don't export outputs fails."" by Francis Murtagh · 2 years ago
  77. a0f8b15 Revert "IVGCVSW-6873 Import inputs but don't export outputs fails." by James Conroy · 2 years ago
  78. 03bf98a IVGCVSW-6873 Import inputs but don't export outputs fails. by Colm Donelan · 2 years, 1 month ago
  79. 311cfa7 MLCE-825: Give reason when workload unsupported for Non Constant Weights/Bias by Francis Murtagh · 2 years, 1 month ago
  80. 80512b0 IVGCVSW-6929 Support for models with implicit expanded dimensions by Mike Kelly · 2 years, 1 month ago
  81. 8bd5360 IVGCVSW-6126 ConstTensorsAsInput: Conv2d - Backends by Cathal Corbett · 2 years, 2 months ago
  82. b4dd5cc IVGCVSW-6124 ConstTensorsAsInput: Conv2d - FrontEnd by Keith Davis · 2 years, 3 months ago
  83. 19e7942 IVGCVSW-6175 Add Pooling3d to Neon by Ryan OShea · 2 years, 2 months ago
  84. 4452baf IVGCVSW-6260 ConstTensorsAsInput: Fully Connected Cl and Neon support. by Cathal Corbett · 2 years, 2 months ago
  85. 4b19d22 IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete ACL by Cathal Corbett · 2 years, 2 months ago
  86. 0302723 IVGCVSW-6936 Sqrt for CpuRef, CpuAcc and GpuAcc by Teresa Charlin · 2 years, 2 months ago
  87. b190da2 IVGCVSW-6862 Use same datatype for all containers of indices in NeonGatherNd by Teresa Charlin · 2 years, 2 months ago
  88. aa80510 IVGCVSW-6862 Modify GATHERNd Neon workload by Teresa Charlin · 2 years, 2 months ago
  89. 06145cc IVGCVSW-6936 Add SQRT support to Neon by Teresa Charlin · 2 years, 2 months ago
  90. 0690265 IVGCVSW-6127 ConstTensorsAsInput: DepthwiseConvolution2d by Cathal Corbett · 2 years, 3 months ago
  91. bd22c7d IVGCVSW-6862 Add GATHERNd Neon workload by Teresa Charlin · 2 years, 2 months ago
  92. 1299496 IVGCVSW-6806 Add Unidirectional Sequence Lstm support to Neon by Mike Kelly · 2 years, 2 months ago
  93. 2776183 IVGCVSW-6706 Move headers to profiling/client/include by Jim Flynn · 2 years, 3 months ago
  94. d83ffe0 IVGCVSW-6839 Unidirectional sequence LSTM test failing in Android S by Cathal Corbett · 2 years, 3 months ago
  95. 4952a3e Revert "Revert "IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl"" by Cathal Corbett · 2 years, 4 months ago
  96. fd5bec4 Revert "Revert "IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon"" by Cathal Corbett · 2 years, 4 months ago
  97. 3826ab6 IVGCVSW-6700 Disable importing on ClConv2d when datalayout is NCHW by David Monahan · 2 years, 4 months ago
  98. f87b90e Revert "IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon" by Cathal Corbett · 2 years, 4 months ago
  99. 79cef69 Revert "IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl" by Cathal Corbett · 2 years, 4 months ago
  100. ad91717 IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl by Cathal Corbett · 2 years, 5 months ago